Intelligent assistant driving method for tunnel boring machine based on big data.

During tunnel construction with tunnel boring machine (TBM), the TBM drivers determine the driving parameters depending only on their own experiences. Inappropriate TBM driving parameters may lead to low construction efficiency, severe disk cutter wear, even tunnel collapse. An assisted driving method for TBM is proposed in this study to assist drivers in determining suitable driving parameters in advance taking into account both the construction safety and efficiency. The proposed method starts with developing a model to classify the grade of surrounding rock masses and a deep learning model to predict the TBM tunneling parameters (i.e., torque and thrust). Then, the models are used to predict the integrity and drivability of the surrounding rock in the tunneling. Finally, appropriate driving parameters for TBM in different rock grades and drivability classes can be determined automatically. This assisted driving method was examined by the data from Yin-song project in China. Essentially, this study can be helpful for the evaluation of rock mass drivability and the determination of driving parameters, paving the way to a self-driving machine in the harsh tunnel boring environment. [ABSTRACT FROM AUTHOR]